© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28586
    Prev
    Next
    INDEX
    Explanations

    travel delays and cancellations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destruir
    0.40
     시장
    0.39
    ConfigFiles
    0.39
     sauve
    0.39
    沉
    0.39
    riline
    0.39
     किफ
    0.38
    轭
    0.38
    lockSeconds
    0.38
     Heating
    0.38
    POSITIVE LOGITS
     disruptions
    1.10
     delays
    1.05
     disruption
    1.00
     cancellations
    0.93
     disrupted
    0.92
     delay
    0.88
     cancelled
    0.81
     canceled
    0.79
     affected
    0.76
     disrupt
    0.75
    Activations Density 0.006%

    No Known Activations